jimothyjohn / nanosam

Fully distilled and accelerated MobileSAM

  • Public
  • 37 runs
  • GitHub
  • Paper
  • License

Run time and cost

This model costs approximately $0.14 to run on Replicate, or 7 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 11 minutes. The predict time for this model varies significantly based on the inputs.

Readme

nanoSAM

Run a highly-accelerated SAM with detection via either bounding box or foreground and background points.

An experiment in TensorRT and accelerated endpoints for edge devices.